Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges
Source
Quim Motger, Marc Oriol, Jordi Marco, Xavier Franch
Author
Quim Motger, Marc Oriol, Jordi Marco, Xavier Franch
Date
Terms in this piece · Glossary
multi-agent — Using several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.
Why it matters
multi-agentUsing several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.Full definition → debate setups have quietly standardized on static fully connected topologies, verbatim exchange, short-term memory and voting — by habit, not evidence. The design space is about a dozen interacting choices most papers leave unstated, which makes cross-study comparison unreliable.
articleEven More Deception: Objective Misalignment in Mixed-Motive LLM Multi-Agent SystemsMarylou Fauchard, Florian Carichon, Margarida Carvalho, Golnoosh FarnadirepoTradingAgentsTauric Research
articleUnderstanding Bugs in Modern Agentic Frameworks: A Study of Symptoms, Root Causes, and Triggering ConditionsXiaowen Zhang, Hannuo Zhang, Shin Hwei Tan